Build Duration Trends

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds value by specifying that it returns all result types (SUCCESS, FAILURE, etc.) and does not support filtering, which is important for the agent to set expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Structured with a clear purpose line, usage guidance, note on filtering, and parameter list. Slight redundancy between the first two sentences ('Build duration trends...' and 'Returns build durations...'), but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description adequately covers the tool's function, supported filters, pagination, and alternative. Lacks explicit mention of output fields (but mitigated by schema), and could add more about edge cases (e.g., empty results).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 0% schema description coverage, the description includes an 'Args' section with short explanations for all 7 parameters (e.g., limit ranges, tenant default). While helpful, descriptions are minimal and could be more detailed (e.g., data types, constraints).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it computes avg/min/max from build durations for trend analysis, distinguishing it from sibling tool get_job_durations by noting it returns ALL results without filtering.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly recommends using this tool to detect performance regressions or timeout-prone jobs, and provides a clear alternative (get_job_durations) for filtered averages, with a note about lack of result filtering.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.